AI agents use trainModel to create or update resources in MongTap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MongTap environment.
An AI agent can call trainModel faster than any human can review — one bad instruction and it creates or modifies resources in MongTap by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Update an existing statistical model with additional sample documents to improve generation quality. It is categorised as a Write tool in the MongTap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MongTap MCP server in PolicyLayer and add a rule for trainModel: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MongTap. Nothing to install.
trainModel is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the trainModel rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for trainModel. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
trainModel is provided by the MongTap MCP server (smallmindsco/mongtap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.